© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80731
    Prev
    Next
    INDEX
    Explanations

    lisa names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ₀
    -0.85
    されています
    -0.80
    webtoken
    -0.77
     survey
    -0.74
     jednot
    -0.74
     sztu
    -0.73
    orca
    -0.71
    stellungen
    -0.70
    weixin
    -0.69
    ängel
    -0.69
    POSITIVE LOGITS
    Lisa
    1.20
     Jennie
    1.16
     Lisa
    1.14
    BLACK
    1.07
     blackpink
    1.04
     BLACK
    0.94
     YG
    0.90
    Lal
    0.90
     lisa
    0.89
    Blink
    0.88
    Activations Density 0.013%

    No Known Activations